Neuro-fuzzy reaping of shear wave velocity correlations derived by hybrid genetic algorithm-pattern search technique

Shear wave velocity is a critical physical property of rock, which provides significant data for geomechanical and geophysical studies. This study proposes a multi-step strategy to construct a model estimating shear wave velocity from conventional well log data. During the first stage, three correlation structures, including power law, exponential, and trigonometric were designed to formulate conventional well log data into shear wave velocity. Then, a Genetic Algorithm-Pattern Search tool was used to find the optimal coefficients of these correlations. Due to the different natures of these correlations, they might overestimate/underestimate in some regions relative to each other. Therefore, a neuro-fuzzy algorithm is employed to combine results of intelligently derived formulas. Neuro-fuzzy technique can compensate the effect of overestimation/underestimation to some extent, through the use of fuzzy rules. One set of data points was used for constructing the model and another set of unseen data points was employed to assess the reliability of the propounded model. Results have shown that the hybrid genetic algorithm-pattern search technique is a robust tool for finding the most appropriate form of correlations, which are meant to estimate shear wave velocity. Furthermore, neuro-fuzzy combination of derived correlations was capable of improving the accuracy of the final prediction significantly.     

Neuro-fuzzy modeling based genetic algorithms for identification of geochemical anomalies in mining geochemistry

A genetic algorithm (GA)-based neuro-fuzzy approach is used for identification of geochemical anomalies by implementing a Takagi, Sugeno and Kang (TSK) type fuzzy inference system in a 5-layered feed-forward adaptive artificial neural network. This paper investigates the effectiveness of GA-based neuro-fuzzy for separating zone dispersed mineralization (ZDM) from blind mineralization, and its application for identification of geochemical anomalies in the arid landscape of the Lut metallogenic province in eastern Iran. Other classification algorithms such as metallometry, zonality, criteria, and back-propagation artificial neural network classifiers are also used for comparison. The genetic operators are carefully designed to optimize the artificial neural network, avoiding premature convergence and permutation problems. The results show that the GA-based hybrid neuro-fuzzy model can provide accurate results in comparison with those results obtained by other techniques. Neuro-fuzzy and GA-based neuro-fuzzy techniques appear to be well-suited for routine exploration geochemistry applications. In conjunction with statistics and conventional mathematical methods, hybrid approaches can be developed and may prove a step forward in the practice of applied geochemistry.     

A comparative study of ANN and Neuro-fuzzy for the prediction of dynamic constant of rockmass

Physico-mechanical properties of rocks have great significance in all operational parts in mining activities, from exploration to final dispatch of material. Compressional wave velocity (p-wave velocity) and anisotropic behaviour of rocks are two such properties which help to understand the rock response under varying stress conditions. They also influence the breakage mechanism of rock. There are different methods to determine thep-wave velocity and anisotropyin situ and in the laboratory. These methods are cumbersome and time consuming. Fuzzy set theory, Fuzzy logic and Neural Networks techniques seem very well suited for typical geotechnical problems. In conjunction with statistics and conventional mathematical methods, hybrid methods can be developed that may prove to be a step forward in modeling geotechnical problems. Here, we have developed and compared two different models, Neuro-fuzzy systems (combination of fuzzy and artificial neural network systems) and Artificial neural network systems, for the prediction of compressional wave velocity.     

Comments on ‘A comparative study of ANN and neuro-fuzzy for the prediction of dynamic constant of rockmass’

Singh et al (2005) examined the potential of the ANN and neuro-fuzzy systems application for the prediction of dynamic constant of rockmass. However, the model proposed by them has some drawbacks according to fuzzy logic principles. This discussion will focus on the main fuzzy logic principles which authors and potential readers should take into consideration.     

Intelligent methods for predicting nuclear magnetic resonance of porosity and permeability by conventional well-logs: a case study of Saharan field

In the well-log data processing, the principal advantage of the nuclear magnetic resonance (NMR) method is the measurement of fluid volume and pore size distribution without resorting to parameters such as rock resistivity. Preliminary processing of the well-log data allowed first to have the petrophysical parameters and then to evaluate the performances of the transverse relaxation time T ₂ NMR. Petrophysical parameters such as the porosity of the formation as well as the effective permeability can be estimated without having recourse the fluid type. The well-log data of five wells were completed during the construction of intelligent models in the Saharan oil field Oued Mya Basin in order to assess the reliability of the developed models. Data processing of NMR combined with conventional well data was performed by artificial intelligence. First, the support vector regression method was applied to a sandy clay reservoir with a model based on the prediction of porosity and permeability. NMR parameters estimated using intelligent systems, i.e., fuzzy logic (FL) model, back propagation neural network (BP-NN), and support vector machine, with conventional well-log data are combined with those of NMR, resulting in a good estimation of porosity and permeability. The results obtained during the processing are then compared to the FL and NN regression models performed by the regression method during the validation stage. They show that the correlation coefficients R ² estimated vary between 0.959 and 0.964, corresponding to the root mean square error values of 0.20 and 0.15.     

补偿模糊神经网络在储层参数预测中的应用

为了克服常规BP神经网络法在预测储层参数中出现学习速度慢、无法结合专家知识等不足，我们引入了补偿模糊神经网络。它是一个结合了补偿模糊逻辑和神经网络的混合系统，由面向控制和面向决策的神经元组成，其模糊运算采用动态的、全局优化运算，学习速度快、学习过程稳定，将其用于储层参数预测效果良好。     

Slake durability study of shaly rock and its predictions

More than 35% of the earths crust is comprised of clay-bearing rocks, characterized by a wide variation in engineering properties and their resistance to short term weathering by wetting and drying phenomenon. The resistance to short-term weathering can be determined by slake durability index test. There are various methods to determine the slake durability indices of weak rock. The effect of acidity of water (slaking fluid) on slake durability index of shale in the laboratory is investigated. These methods are cumbersome and time consuming but they can provide valuable information on lithology, durability and weather ability of rock. Fuzzy set theory, Fuzzy logic and Artificial Neural Networks (ANN) techniques seem very well suited for typical complex geotechnical problems. In conjunction with statistics and conventional mathematical methods, a hybrid method can be developed that may prove a step forward in modeling geotechnical problems. During this investigation a model was developed and compared with two other models i.e., Neuro-fuzzy systems (combination of fuzzy and artificial neural network systems) and artificial neural network system, for the prediction of slake durability index of shaly rock to evaluate the performance of its prediction capability.     

油气储层裂缝定量描述及其地质意义

在裂缝型油气藏勘探开发过程中,裂缝发育区带、裂缝密度以及连通性是影响生产的关键参数。文章在详细综述储层裂缝定量描述的必要性、地质意义、分维描述、人工智能模糊描述及微观描述等定量描述法的基础上,介绍了裂缝系统各参数之间的关系及裂缝预测方法,进而介绍了定量描述法在裂缝预测中应用的几个实例。     

A study of soft computing models for prediction of longitudinal wave velocity

Genetic algorithm (GA) and support vector machine (SVM) optimization techniques are applied widely in the area of geophysics, civil, biology, mining, and geo-mechanics. Due to its versatility, it is being applied widely in almost every field of engineering. In this paper, the important features of GA and SVM are discussed as well as prediction of longitudinal wave velocity and its advantages over other conventional prediction methods. Longitudinal wave measurement is an indicator of peak particle velocity (PPV) during blasting and is an important parameter to be determined to minimize the damage caused by ground vibrations. The dynamic wave velocity and physico-mechanical properties of rock significantly affect the fracture propagation in rock. GA and SVM models are designed to predict the longitudinal wave velocity induced by ground vibrations. Chaos optimization algorithm has been used in SVM to find the optimal parameters of the model to increase the learning and prediction efficiency. GA model also has been developed and has used an objective function to be minimized. A parametric study for selecting the optimized parameters of GA model was done to select the best value. The mean absolute percentage error for the predicted wave velocity (V) value has been found to be the least (0.258 %) for GA as compared to values obtained by multivariate regression analysis (MVRA), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), and SVM.     

A Hybrid Neuro-Fuzzy Model for Mineral Potential Mapping

A GIS-based hybrid neuro-fuzzy approach to mineral potential mapping implements a Takagi–Sugeno type fuzzy inference system in a four-layered feed-forward adaptive neural network. In this approach, each unique combination of predictor patterns is considered a feature vector whose components are derived by knowledge-based ordinal encoding of the constituent predictor patterns. A subset of feature vectors with a known output target vector (i.e., unique conditions known to be associated with either a mineralized or a barren location), extracted from a set of all feature vectors, is used for the training of an adaptive neuro-fuzzy inference system. Training involves iterative adjustment of parameters of the adaptive neuro-fuzzy inference system using a hybrid learning procedure for mapping each training vector to its output target vector with minimum sum of squared error. The trained adaptive neuro-fuzzy inference system is used to process all feature vectors. The output for each feature vector is a value that indicates the extent to which a feature vector belongs to the mineralized class or the barren class. These values are used to generate a favorability map. The procedure is applied to regional-scale base metal potential mapping in a study area located in the Aravalli metallogenic province (western India). The adaptive neuro-fuzzy inference system demarcates high favorability zones occupying 9.75% of the study area and identifies 96% of the known base metal deposits. This result is significant both in terms of reduction in search area and the percentage of deposits identified.     

Prediction of the Rock Mass Diggability Index by Using Fuzzy Clustering-Based,ANN and Multiple Regression Methods

Rock mass classification systems are one of the most common ways of determining rock mass excavatability and related equipment assessment. However, the strength and weak points of such rating-based classifications have always been questionable. Such classification systems assign quantifiable values to predefined classified geotechnical parameters of rock mass. This causes particular ambiguities, leading to the misuse of such classifications in practical applications. Recently, intelligence system approaches such as artificial neural networks (ANNs) and neuro-fuzzy methods, along with multiple regression models, have been used successfully to overcome such uncertainties. The purpose of the present study is the construction of several models by using an adaptive neuro-fuzzy inference system (ANFIS) method with two data clustering approaches, including fuzzy c-means (FCM) clustering and subtractive clustering, an ANN and non-linear multiple regression to estimate the basic rock mass diggability index. A set of data from several case studies was used to obtain the real rock mass diggability index and compared to the predicted values by the constructed models. In conclusion, it was observed that ANFIS based on the FCM model shows higher accuracy and correlation with actual data compared to that of the ANN and multiple regression. As a result, one can use the assimilation of ANNs with fuzzy clustering-based models to construct such rigorous predictor tools.     

基于人工神经网络的三峡库区丰都县水库塌岸预测

为了建立一个适合于三峡库区的塌岸预测方法体系,采用具有处理非线性关系功能的人工神经网络方法对水库塌岸问题进行研究。通过训练、学习和仿真,获得预测正确率为97.2%的具有7-32-14网络结构的BP神经网络模型,采用该模型对蓄水位为175　m时丰都县各岸段进行塌岸预测,并将预测结果与传统经验公式计算法所得结果及实际监测数据进行对比。结果表明:基于人工神经网络的塌岸预测宽度与实际监测数据很接近,偏差在5 m以内;公式法计算结果与监测值平均偏差为15.9 m,而且对于部分坡段,公式法计算结果比实际监测值小8～11 m,没能预测出塌岸的真正范围。采用神经网络模型对丰都县水库进行塌岸预测,预测结果与实际监测数据平均偏差约3.8%,表明其预测结果可靠。     

水流模拟智能化问题的探讨

对水流模拟的发展历史进行了总结,指出阻碍水流模拟发展的主要问题,提出克服这些瓶颈问题的方法是将智能科学与水利科学交叉融合,实现水流的智能模拟。据此,介绍了水流智能模型理论,结合遗传算法、模糊逻辑、元胞自动机、混沌分析理论、人工神经网络、专家系统、数据挖掘等智能理论和技术,对水流智能模拟的实现途径作了探讨,并指出建造一个优秀的水流模拟智能系统的关键是联合运用各种智能方法,认为智能化是当前水流模拟发展的新方向,水流智能模型将是水利科学的一种新的研究途径,并将在研究水流问题上具有广阔的应用前景。     

基于自适应神经-模糊推理系统的软土路基沉降预测模型

针对目前软基沉降预测中最常用的生长曲线模型以及人工神经网络模型的不足,提出将自适应神经模糊推理系统(ANFIS)应用于软基沉降预测。ANFIS将专家的模糊推理过程蕴含于神经网络结构中,使神经网络的结点和权值具有明确的物理意义,避免了传统神经网络工作过程的"黑盒"性。同时该系统可以采用最小二乘法和梯度下降法相结合的混合算法,既具有神经网络的自适应性和学习能力,又克服了它的局部极小值等缺点,预测精度也远高于生长曲线模型。最后用工程实例与生长模型和神经网络模型进行了对比,结果表明:ANFIS模型优于这两种模型,特别是在模拟多输入变量、高维数下软基沉降预测问题时有着独特的优势,具有一定的推广应用价值。     

Optimal water and waste load allocation in reservoir–river systems: a case study

In this paper, a new methodology is developed for optimization of water and waste load allocation in reservoir–river systems considering the existing uncertainties in reservoir inflow, waste loads and water demands. A stochastic dynamic programming (SDP) model is used to optimize reservoir operation considering the inflow uncertainty, and another model called PSO-SA is developed and linked with the SDP model for optimizing water and waste load allocation in downstream river. In the PSO-SA model, a particle swarm optimization technique with a dynamic penalty function for handling the constraints is used to optimize water and waste load allocation policies. Also, a simulated annealing technique is utilized for determining the upper and lower bounds of constraints and objective function considering the existing uncertainties. As the proposed water and waste load allocation model has a considerable run-time, some powerful soft computing techniques, namely, Regression tree Induction (named M5P), fuzzy K-nearest neighbor, Bayesian network, support vector regression and an adaptive neuro-fuzzy inference system, are trained and validated using the results of the proposed methodology to develop real-time water and waste load allocation rules. To examine the efficiency and applicability of the methodology, it is applied to the Dez reservoir–river system in the south-western part of Iran.     

焉耆盆地宝浪油田宝中区块波阻抗反演储层预测

笔者采用波阻抗反演技术，对新疆焉耆盆地宝浪油田宝中区块8个小的砂体厚度进行了横向预测。该方法的关键在于对测井资料的应用，也就是测井的约束条件，使得反演结果具有较高分辨率和可靠性。通过预测，认清了该区块砂体从上至下的分布规律，克服了“一孔之见”的缺陷，增强了预见性，减少了风险性，为编制开发方案奠定了基础。     

模糊神经网络用于储层预测

利用模糊理论和ＢＰ网络相结合组成的模糊神经网络系统,能够克服ＢＰ网络单独使用的局限性,可在地质条件较复杂地区进行储层及油气预测。通过实际资料应用表明,应用单个ＢＰ网络进行储层及油气预测效果较差的地区,采用模糊神经网络能取得较好的效果。     

Fluid Property Discrimination in Dolostone Reservoirs Using Well Logs

The Ordovician Majiagou Formation is one of the main gas-producing strata in the Ordos Basin,China.The identification of hydrocarbon-bearing intervals via conventional well logs is a challenging task.This study describes the litholog of Ma 5(Member 5 of Majiagou Formation)dolostones,and then analyzes the responses of various conventional well logs to the presences of natural gas.The lithology of the gas bearing layers is dominantly of the dolomicrite to fine to medium crystalline dolomite.Natural gas can be produced from the low resistivity layers,and the dry layers are characterized by high resistivities.Neutron-density crossovers are not sensitive to the presences of natural gas.In addition,there are no significant increases in sonic transit times in natural gas bearing layers.NMR(nuclear magnetic resonance)logs,DSI(Dipole Sonic Imager)logs and borehole image logs(XRMI)are introduced to discriminate the fluid property in Majiagou dolostone reservoirs.The gas bearing intervals have broad NMR T_2(transverse relaxation time)spectrum with tail distributions as well as large T_(2gm)(T_2 logarithmic mean values)values,and the T_2 spectrum commonly display polymodal behaviors.In contrast,the dry layers and water layers have low T_(2gm) values and very narrow T_2 spectrum without tails.The gas bearing layers are characterized by low V_p/V_s ratios,low Poisson’s ratios and low P-wave impedances,therefore the fluid property can be discriminated using DSI logs,and the interpretation results show good matches with the gas test data.The apparent formation water resistivity(AFWR)spectrum can be derived from XRMI image logs by using the Archie’s formula in the flushed zone.The gas bearing layers have broad apparent formation water resistivity spectrum and tail distributions compared with the dry and water layers,and also the interpretation results from the image logs exhibit good agreement with the gas test data.The fluid property in Majiagou dolostone reservoirs can be discriminated through NMR logs,DSI logs and borehole image logs.This study helps establish a predictable model for fluid property in dolostones,and have implications in dolostone reservoirs with similar geological backgrounds worldwide.     

基于混合模糊神经网络储层裂缝地震反演研究

基于储层裂缝系统具有非线性特征,储层裂缝地震反演是由遗传算法(GA)、模糊神经网络(ANF IS)和禁忌搜索算法(TS)有机地结合而构成的自适应混合模糊神经网络技术。该技术在成像测井约束下,形成的自适应混合算法分别训练ANF IS网络的前提参数和结论参数,从而获得满足精度要求的储层裂缝密度的最佳估计值。针对目标储层段,应用储层裂缝地震反演方法对过井地震剖面和联井地震剖面进行了储层裂缝密度反演处理,获得了可用于地质解释和油气预测的视裂缝密度剖面。这种裂缝密度剖面含有裂缝定量信息,其裂缝密度相对误差为:0.8%~24%,满足勘探开发的要求。经与研究区的地质对比分析表明,视裂缝密度剖面上的裂缝展布特征符合研究区的沉积相分布和岩石力学性质的变化特征,对研究区的勘探开发具有重要意义。